Estimate a ridge using the modified corona method (modified cost function).
coronoid(tfrep, guess, tfspec=numeric(dim(tfrep)[2]), subrate=1,
temprate=3, mu=1, lambda=2 * mu, iteration=1000000, seed=-7,
stagnant=20000, costsub=1, plot=TRUE)
Estimate for the contribution of the noise to modulus.
Initial guess for the algorithm.
Estimate for the contribution of the noise to modulus.
Subsampling rate for ridge estimation.
Initial value of temperature parameter.
Coefficient of the ridge's derivative in cost function.
Coefficient of the ridge's second derivative in cost function.
Maximal number of moves.
Initialization of random number generator.
Maximum number of stationary iterations before stopping.
Subsampling of cost function in output.
When set(default), some results will be shown on the display.
Returns the estimated ridge and the cost function.
1D array (of same length as the signal) containing the ridge.
1D array containing the cost function.
The returned cost may be a large array. The argument costsub allows subsampling the cost function.
To accelerate convergence, it is useful to preprocess modulus before
running annealing method. Such a preprocessing (smoothing and
subsampling of modulus) is implemented in coronoid
. The
parameter subrate specifies the subsampling rate.
See discussion in text of ``Practical Time-Frequency Analysis''.